智能科学与技术学报 ›› 2021, Vol. 3 ›› Issue (2): 172-178.doi: 10.11959/j.issn.2096-6652.202117

• 专题:智能交通系统与应用 • 上一篇    下一篇

一种考虑时空关联的深度学习短时交通流预测方法

张阳1, 胡月1, 辛东嵘2   

  1. 1 福建工程学院交通运输学院,福建 福州 350118
    2 福建工程学院土木工程学院,福建 福州 350118
  • 修回日期:2021-03-02 出版日期:2021-06-15 发布日期:2021-06-01
  • 作者简介:张阳(1983- ),男,博士,福建工程学院交通运输学院副教授,主要研究方向为智能交通信息处理、交通大数据处理、交通流预测
    胡月(1997- ),女,福建工程学院交通运输学院硕士生,主要研究方向为交通运输规划与管理
    辛东嵘(1986- ),女,博士,福建工程学院土木工程学院副教授,主要研究方向为人工智能、智能交通
  • 基金资助:
    国家自然科学基金资助项目(51678077);福建省自然科学基金资助项目(2019J01781);福建省自然科学基金资助项目(2020J05194);福建省财政厅科技计划项目(GY-Z21001)

A deep learning short-term traffic flow prediction method considering spatial-temporal association

Yang ZHANG1, Yue HU1, Dongrong XIN2   

  1. 1 School of Transportation, Fujian University of Technology, Fuzhou 350118, China
    2 School of Civil Engineering, Fujian University of Technology, Fuzhou 350118, China
  • Revised:2021-03-02 Online:2021-06-15 Published:2021-06-01
  • Supported by:
    The National Natural Science Foundation of China(51678077);The Natural Science Foundation of Fujian Province(2019J01781);The Natural Science Foundation of Fujian Province(2020J05194);Fujian Finance Department Science Foundation(GY-Z21001)

摘要:

空间关联特性的关联因素过于复杂且难以量化等问题导致短时交通流预测过于依赖时间关联特性。针对这一问题,提出一种考虑时空关联的深度学习短时交通流预测方法。首先,通过构建同时考虑距离、车流流量相似性和车流速度相似性的空间关联性度量函数,量化目标路段与周边关联道路间的空间关联性。然后,构建内嵌长短时记忆神经元的卷积神经网络模型,利用长短时记忆神经元提取数据间的时间关联性,利用空间关联性度量值及交通数据的卷积传输提取数据间的空间关联性,以实现同时考虑时空关联性的交通流预测。实验结果表明,提出的方法能适应工作日和周末等不同交通流特性条件下的短时预测,且与经典方法相比,预测精度更优,在工作日和周末的预测偏差分别为10.45%和12.35%。

关键词: 深度学习, 智能交通, 交通预测, 长短时记忆神经网络, 卷积神经网络

Abstract:

The short-term traffic flow prediction is too dependent on the time correlation characteristics, which due to the problems that the correlation factors of the spatial correlation characteristics are too complicated and difficult to quantify.In response to this defect, a deep learning short-term traffic flow prediction method considering spatial-temporal association was proposed.Firstly, by constructing a spatial association measurement function that simultaneously considers distance, flow similarity, and speed similarity, the spatial correlation between the target road segment and the surrounding associated road segments was quantified and predicted.Then, a convolutional neural network model with long short-term memory neurons embedded was constructed.The long short-term memory neurons were used to extract the temporal correlation characteristics between the data, and the spatial correlation metric and the convolution transmission of traffic data were used to extract the spatial correlation characteristics between the data, so as to realize the traffic flow prediction considering the spatial-temporal association.The experimental results show that the proposed method can adapt to short-term forecasting under different traffic flow characteristics such as weekdays and weekends, and the prediction accuracy is better than that of the classical methods.In weekdays and weekends, the forecast bias are 10.45% and 12.35% respectively.

Key words: deep learning, intelligent transportation, traffic prediction, long short-term memory neural network, convolu-tional neural network

中图分类号: 

No Suggested Reading articles found!